A method and system for visualizing and tracing mechanical structure vibration energy of a stator support

Abstract

The present application belongs to the field of engine technology, and discloses a kind of support stator mechanical structure vibration energy visualized tracing method, the vibration response transmission law research of aero-engine support system;Aero-engine support system vibration response signal transmission rule test and analysis research;Aero-engine support system vibration response signal prediction based on deep learning;The vibration signal tracing technology research of a certain type aero-engine support system;Realize aero-engine vibration energy visualization technology;Aero-engine support system vibration response signal transmission rule test and analysis research;Aero-engine support system vibration response signal prediction based on deep learning;The vibration signal tracing technology research of a certain type aero-engine support system.The present application can be transplanted to the fault diagnosis and health management of the turbofan engine under research in our country, and provides technical support for the design of new turbofan engine, and also can provide theoretical basis for aero-engine support system parameter optimization design, military and economic value is huge.

Description

Technical Field

[0001] This invention belongs to the field of engine technology, and in particular relates to a method and system for visually tracing the vibration energy of a supporting stator mechanical structure. Background Technology

[0002] Rotating machinery is widely used in aerospace, automotive, and marine equipment. Due to the highly complex operating conditions of rotating machinery, and the ease with which vibration signals are distorted and submerged during transmission through complex structures and accessory systems, cross-structural system faults are among the most easily overlooked and difficult-to-eliminate vibration faults. Aero-engines are extremely complex thermodynamic rotating machines. Many components operate under high temperature, high pressure, high-speed rotation, strong vibration, and complex and variable environmental conditions, frequently enduring high loads and thermal shocks. Their extremely harsh working environment makes them prone to failure, exhibiting significant characteristics such as multiple failure modes and multi-mode composite failures. Accurately describing the transmission law of vibration signals in aero-engine systems and the contribution of each transmission path is a challenge in diagnosing certain primary faults. Achieving rapid vibration source tracing can effectively guide fault diagnosis and mitigation efforts, and in recent years, research on vibration transmission mechanisms has become a hot topic in the field.

[0003] The vibration response transmission law refers to the transmission relationship between the bearing housing response and the response on the outside of the engine casing. This relationship is many-to-many, meaning that the excitation from each bearing housing is transmitted to all points on the outside of the engine casing, and any point on the outside of the casing receives responses from the excitations of each bearing housing. The superposition of these responses determines the characteristics of the vibration response signal. Therefore, the transmission law here is not a simple point-to-point transmission, but rather the combined effect of multiple excitation sources at that point. How can we use intuitive visualization methods to characterize the general laws of the above mechanical phenomena? What are the characteristics of these laws for aero-engine products? It is urgent to summarize and refine these scientific questions for further research.

[0004] Furthermore, the main reason why no software in China can currently perform automatic power flow visualization is that the calculation and visualization of vibration energy requires substantial computational resources. The vibration state at every moment requires complex mathematical calculations, including dynamic analysis and frequency analysis. Although technically feasible, most industrial simulation software currently does not support real-time vibration energy visualization due to limitations in cost, performance, and practical needs. However, vibration energy visualization technology provides an effective tool for the health management of aero-engines, enabling early warning of potential problems, performance optimization, and ensuring flight safety. The application of these technologies is crucial for the reliability and efficiency of the modern aviation industry. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention provides a method for visualizing and tracing the source of vibration energy in a supporting stator mechanical structure.

[0006] This invention is implemented as follows: a method for visualizing and tracing the vibration energy of a supporting stator mechanical structure, the technology comprising:

[0007] S1: Study on the vibration response transmission law of aero-engine support system;

[0008] S2: Experimental and analytical study on the transmission law of vibration response signal in aero-engine support system;

[0009] S3: Vibration response signal prediction of aero-engine support system based on deep learning;

[0010] S4: Research on vibration signal tracing technology of a certain type of aircraft engine support system;

[0011] S5: Enables visualization technology for vibration energy of aero-engines;

[0012] S6: Experimental and analytical study on the transmission law of vibration response signal in aero-engine support system;

[0013] S7: Vibration response signal prediction of aero-engine support system based on deep learning;

[0014] Research on vibration signal tracing technology of S8 type aero-engine support system.

[0015] Further, Step 0: Program begins;

[0016] Step 1: Input and define material properties and finite element types through the material and element interface;

[0017] Step 2: Input the geometric parameters of the research object through the structural model command interface and create a geometric model;

[0018] Step 3: Input the material properties, element types, and geometric models generated in Step 1 and 2 into the ANSYS preprocessing module ( / PREP) to create a finite element model of the research object;

[0019] Step 4: Input the load properties and application location through the load condition command interface to apply the excitation load to the finite element model created in Step 3;

[0020] Step 5: Apply constraints to the finite element model created in Step 3 by inputting the constraint type and application location through the boundary condition command interface;

[0021] Step 6: Enter the ANSYS solver module ( / SOLU). Input the dynamic solution type and related settings parameters through the solver settings command interface;

[0022] Step 7: Solve;

[0023] Step 8: Enter the ANSYS post-processing module ( / POST). Use the post-processing settings command interface to input the analysis time, data extraction location, data type, and data output save location, etc.

[0024] Step 9: Extract and output the parameters such as internal forces and velocities from the finite element model of the research object and save them to the file system;

[0025] Step 10, the self-compiling calculation program, will also execute the following sub-steps:

[0026] Sub step 1: Read the ANSYS output calculation result file and element node relationship file from the file system, and organize them into a matrix and store them in the workspace;

[0027] Sub step 2: MATLAB reads the element coordinate system and nodal coordinates of the finite element model

[0028] The coordinate system and the result coordinate system are used to transform between physical space and computational space;

[0029] Sub step 3: Construct the computational domain for the structural acoustic intensity vector field;

[0030] Sub step 4: Based on the relevant calculation formulas, solve the structural acoustic intensity vector of each unit in the computational domain, and write it into the result matrix according to the relationship between the unit nodes;

[0031] Sub step 5: Output the structural acoustic intensity calculation results and save them to the file system;

[0032] Step 11: For the transient structural acoustic intensity vector field, the communication mechanism continues to control the calculation process, looping through Steps 8 to 10, outputting the structural acoustic intensity calculation results files at different times and saving them to a file.

[0033] The system continues processing until all analysis timelines are complete;

[0034] Step 12: The post-processing software TECPLOT reads the constructed computational domain;

[0035] Step 13: The TECPLOT software reads the macro file, reads the calculated structural acoustic intensity result file from the file system, and draws the structural acoustic intensity vector diagram;

[0036] Step 14: The TECPLOT software reads the macro file and saves the structural acoustic intensity vector diagram to the specified file directory;

[0037] Step 15: For the transient structural acoustic intensity vector field, repeat Step 12 to Step 14 until the structural acoustic intensity vector field for all analysis times is plotted and saved.

[0038] Step 16: The program ends and exits S.

[0039] Furthermore, S1 specifically includes:

[0040] Based on the simulation structure of the aero-engine support system, an improved blind source separation algorithm is proposed based on information theory and maximum entropy algorithm. This algorithm decomposes the vibration response signals at each measuring point of the casing and determines the characterization relationship between the signals. Combined with the power flow frequency response function, the transmission law of transient / steady-state total vibration energy and vibration energy components between the bearing housing and the casing is studied.

[0041] (1) Research on the theoretical basis of structural acoustic intensity method / vibration wave;

[0042] (2) Compile the trace visualization code to basically realize energy trace visualization.

[0043] Furthermore, S2 specifically includes:

[0044] To address the vibration transmission problem in aero-engine support systems, this study utilizes the obtained vibration response signals of the casing and investigates the excitation-response mapping relationship. This allows for a deeper exploration of the interrelationships between vibration signals at various measuring points of the casing under different excitations, ultimately revealing the transmission law of the vibration response.

[0045] (1) Establish a simplified finite element model and mesh generation for the support system;

[0046] (2) Select response measurement points to obtain the amplitude-frequency characteristic curve of the outer casing under applied excitation;

[0047] (3) Analyze the transient vibration signals of the response measurement points under fixed frequency (50Hz / 100Hz / 150Hz) for single-point excitation (supports 1, 2, and 3) and multi-point excitation (supports 1, 2 / 2, 3 / 1, 3 / 1, 2, and 3).

[0048] Furthermore, S3 specifically includes:

[0049] Based on the dynamic model of the aero-engine support system and the obtained casing vibration response signal, the LSTM model is used to model and predict time series data, analyze the prediction capability of casing measurement point vibration signal, and realize the prediction of single structure and cross structure vibration signals of aero-engine in response to the specific needs of aero-engine health management.

[0050] (1) Acquisition of vibration signals from three sampling points in the outer casing of the dual-rotor system;

[0051] (2) The CNNLSTM model is trained using vibration signals from three sampling points to achieve accurate prediction of the third time-domain vibration signal when only two vibration signals are input.

[0052] (3) Accurate prediction of spectral characteristics of time-domain signals by fast Fourier transform.

[0053] Furthermore, S4 specifically includes:

[0054] To address the issue of vibration tracing in the stator casing, this study investigates vibration signal tracing technology for a certain type of aero-engine support system under single / multi-point excitation conditions, based on the established model and research on the vibration response transmission law of the support system. Furthermore, the abnormal vibration diagnosis capability of the proposed single-excitation vibration signal tracing technology is tested to verify the effectiveness and accuracy of the proposed tracing technology.

[0055] (1) The first generation of vibration source traceability response dictionary and signal source traceability verification (based on four-point acceleration response vibration signal of outer casing under single-point excitation) was established.

[0056] (2) Complete the research on the method of establishing the response dictionary for the Nth generation of response vibration.

[0057] Furthermore, S5 specifically includes:

[0058] The structural acoustic intensity method was extended to a matrix form and applied to the field of aero-engines. Using a computational system built with finite element tools and a self-compiling program, the transient and steady-state total structural acoustic intensity field of the casing, as well as the structural acoustic intensity fields of longitudinal waves, shear waves, torsional waves, and bending waves, were solved and visualized under the excitation of unbalanced forces on high and low-pressure rotors. The transmission characteristics and distribution patterns of the transient and steady-state vibration energy carried by these four vibration waves on the casing were analyzed. Furthermore, the intrinsic physical relationship between structural acoustic intensity and structural vibration characteristics was derived and analyzed through equations of motion.

[0059] Furthermore, S6 specifically includes:

[0060] (1) Harmonic response analysis of the aircraft engine support system model;

[0061] (2) Transient response analysis of the aircraft engine support system model.

[0062] Furthermore, S7 specifically includes: studying how to effectively utilize LSTM models to predict aero-engine sensor data containing missing signals, and enhancing the expression and application of these predictions through vibration energy visualization technology.

[0063] Furthermore, S8 specifically includes:

[0064] To address the energy dispersion caused by discontinuous support structures, this paper proposes a new vibration signal separation and identification method by extending the signal feature enhancement method based on geometric peak modification, starting from the geometric modification of the signal. Furthermore, based on the similarities and differences of excitation signals in different parts, the paper explores the rank and sparsity characteristics of vibration signals, proposes a novel separation and identification framework, and finally obtains the mapping relationship between the excitation source and the response of the casing measuring point.

[0065] For a certain type of engine support system, using the excitation signal and the vibration response model of the casing, the transient / steady-state total vibration energy and energy components of the support system are obtained through the Lagrange method. Combined with the power flow frequency response function, the energy transfer path between multiple bearing seats and the casing is studied. Subsequently, the proposed synchronous oscillation source tracing method is further extended, fully considering the design scenarios for specific models and engineering realities. For scenarios where subsynchronous oscillations in actual systems have multiple inducing conditions, a support system source tracing model based on a multi-source domain adaptive algorithm is established, and a subsynchronous oscillation source tracing method that is effective under multiple inducing conditions is proposed.

[0066] Finally, based on open-loop mode resonance theory, an excitation source inversion method in the equivalent system is proposed. Combining the mapping relationship dataset between excitation signal and response signal, a synchronous oscillation source tracing model based on multi-source domain adaptive network is established, and a casing vibration source tracing method under single / multi-point excitation conditions is developed.

[0067] Another object of the present invention is to provide a computer device, the computer device including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor causing the processor to perform the steps of the method for visualizing and tracing the vibration energy of the supporting stator mechanical structure.

[0068] Another object of the present invention is to provide a system for visual tracing of vibration energy in an aircraft engine support system, the system comprising:

[0069] A vibration signal decomposition module is used to decompose the vibration response signals of each measuring point of the casing and determine the characterization relationship between the signals based on the simulation structure of the aero-engine support system and the blind source separation algorithm developed using information theory and maximum entropy algorithm.

[0070] A vibration energy transfer analysis module is used to study the transmission law of transient and steady-state total vibration energy and vibration energy components between the bearing housing and the casing by combining the power flow frequency response function;

[0071] A trace visualization module is used to compile trace visualization code to realize the visual representation of energy traces;

[0072] A data storage module for storing processed vibration response signals and energy trace data.

[0073] Another object of the present invention is to provide a system for studying vibration transmission in an aero-engine support system, the system comprising:

[0074] A finite element model building module is used to establish a simplified finite element model of the support system and perform mesh generation for the vibration transmission problem of the aero-engine support system.

[0075] An excitation-response analysis module is used to analyze the excitation-response mapping relationship in depth using the obtained casing vibration response signal, and to reveal the transmission law of vibration response;

[0076] An experimental simulation module is used to analyze the transient vibration signals of the response measurement points under single-point excitation and multi-point excitation at a constant frequency.

[0077] A data output module is used to output the analysis results of the vibration transmission law.

[0078] Another object of the present invention is to provide a system for vibration signal prediction and spectral characteristic analysis of an aero-engine support system, the system comprising:

[0079] A time series modeling module is used to perform time series modeling and prediction of casing vibration response signals based on the dynamic model of the aero-engine support system and the LSTM model.

[0080] A vibration signal prediction module is used to accurately predict time-domain vibration signals by acquiring and training vibration signals from three sampling points in the outer casing of a dual-rotor system.

[0081] A spectral feature analysis module is used to perform a fast Fourier transform on the predicted time-domain signal to obtain accurate predictions of spectral features.

[0082] A health management support module for using prediction and analysis results for the health management of aero engines.

[0083] Another object of the present invention is to provide a system for vibration tracing of an aircraft engine support system, the system comprising:

[0084] A signal feature enhancement module is proposed to address the energy dispersion problem caused by discontinuities in the support structure. A signal feature enhancement method based on geometric peak modification is proposed to improve the accuracy of vibration signal separation and identification.

[0085] A subsynchronous oscillation tracing module is used to establish a support system tracing model based on a multi-source domain adaptive algorithm for subsynchronous oscillation under multi-source induced conditions, and to propose an effective subsynchronous oscillation tracing method.

[0086] An excitation source inversion module is used to perform excitation source inversion in an equivalent system based on open-loop mode resonance theory, and to construct a synchronous oscillation source tracing model of a multi-source domain adaptive network by combining the mapping relationship dataset between excitation signal and response signal.

[0087] A vibration tracing module is used to implement casing vibration tracing under single / multi-point excitation conditions.

[0088] Based on the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solution to be protected by this invention are as follows:

[0089] First, the structural acoustic intensity method is a method that calculates acoustic intensity by measuring the velocity and pressure on a structural surface, thereby analyzing the energy transfer path and distribution within the structure. In the study of vibration energy in aero-engines, this method is used to describe the flow of vibration energy in detail. By combining force and velocity measurements, the structural acoustic intensity method can not only help engineers identify the source and location of energy dissipation, but also clearly show the energy flow path in various engine components through vector field visualization.

[0090] The application of this technology enables engineers to perform vibration analysis and control more precisely. For example, during the engine design and testing phases, the structural acoustic intensity method can be used to evaluate the effectiveness of different design schemes for vibration control, optimize structural design, reduce unnecessary energy loss, and extend engine lifespan. Furthermore, this method can help maintenance personnel identify fault locations during routine maintenance, allowing for targeted maintenance and repairs.

[0091] With the development of artificial intelligence technology, deep learning models, especially Long Short-Term Memory (LSTM) networks and Convolutional LSTM networks (CNNLSTM), have been widely used in the prediction and analysis of time series data. In the monitoring of vibration energy in aero-engines, these models are used to model and predict vibration signals, enabling real-time monitoring and early warning of engine vibration status.

[0092] By training deep learning models, vibration patterns can be learned from historical vibration data to predict future vibration trends. This prediction not only helps detect potential abnormal vibrations but also allows for timely intervention before engine failures occur, preventing serious mechanical damage. Furthermore, this technology enables real-time monitoring of vibration conditions during engine testing and operation, optimizing engine operating parameters and improving engine efficiency and safety.

[0093] Vibration signal tracing technology refers to the technique of tracking the source and propagation path of vibration through in-depth analysis of vibration signals. This research direction is particularly important in aero-engine vibration energy visualization technology. By establishing a vibration transmission model, it is possible to analyze how vibration propagates from the source to other components of the engine, which is of great significance for diagnosing faults and optimizing vibration control strategies.

[0094] The application of this technology not only helps engineers more accurately identify the specific sources of vibration, but also analyzes the specific mechanisms of vibration propagation, providing a scientific basis for engine design and maintenance. For example, during the engine design phase, by simulating the vibration propagation path, structural design can be predicted and optimized to reduce unnecessary vibrations. During the maintenance phase, this technology can help maintenance personnel accurately locate the source of faults, improving maintenance efficiency and quality.

[0095] The development of vibration energy visualization technology for aero-engines, particularly the application of structural acoustic intensity methods, the integration of deep learning models, and research on vibration signal tracing technology, has greatly improved the ability to monitor and analyze the vibration status of aero-engines. The combined application of these technologies not only improves engine operating efficiency and safety but also plays a crucial role in engine design, testing, and maintenance, providing essential support for aero-engine health management and fault diagnosis.

[0096] Secondly, this invention applies rotor mechanical vibration energy visualization technology to practical engineering problems, enabling vibration transmission analysis and source tracing to be implemented in aero-engine support systems. This expands the research approach for overall aero-engine vibration and fault diagnosis, helping relevant enterprises intuitively understand the distribution law of rotor mechanical vibration energy. It also assists in conducting research on vibration transmission laws and source tracing of aero-engine support systems under multi-source excitation conditions, and there is an urgent need to develop source identification technology for vibration signals from a certain type of engine casing under multi-source excitation. The research results will have extremely high guiding significance for a deeper understanding of vibration transmission and nonlinear dynamic behavior of aero-engine support systems, and will have important application value for improving the structural integrity and reliability of a certain turbofan engine. It can be used for batch maintenance of a certain engine, significantly reducing maintenance costs. This technical method can be transferred to fault diagnosis and health management of turbofan engines under development in my country, and will provide technical support for the design of new turbofan engines. It can also provide a theoretical basis for the parameter optimization design of aero-engine support systems, with enormous military and economic value.

[0097] Third, as supplementary evidence of the inventive step of the claims of this invention, it is also reflected in the following important aspects:

[0098] (1) The expected benefits and commercial value of the technical solution of this invention after transformation are as follows:

[0099] ① Extend engine life

[0100] By monitoring and analyzing vibration energy, the health status of the stator structure can be assessed more accurately, maintenance and upkeep strategies can be optimized, unnecessary downtime and repairs can be reduced, thereby extending engine life and reducing operating costs.

[0101] ② Improve operational efficiency

[0102] Vibration energy visualization and tracing technology can help airlines and engine manufacturers diagnose and repair faults more efficiently, improve engine operating efficiency, reduce downtime, and increase aircraft utilization and flight punctuality.

[0103] ③ Reduce maintenance costs

[0104] Early detection and prediction of faults can reduce the occurrence of sudden failures and lower the cost of emergency repairs and parts replacements. At the same time, optimized maintenance plans can reduce waste of human and material resources and improve the efficiency of maintenance work.

[0105] ④ Technological barriers

[0106] This invention possesses high technological barriers, enabling it to create a significant competitive advantage. Mastering this technology allows one to gain a leading position in the market, fill market gaps, and acquire a larger market share.

[0107] ⑤ Additional Services

[0108] In addition to the technology itself, related consulting, training, maintenance and other value-added services can be provided to form a complete solution and increase revenue streams.

[0109] (2) The technical solution of this invention fills a technical gap in the industry both domestically and internationally:

[0110] ① Currently, there is no commercial simulation analysis software in China that can perform visualized analysis of vibration energy.

[0111] ② International commercial simulation analysis software has made slow progress in the development of this technology. Attached Figure Description

[0112] Figure 1 This is the technical route for visualizing the vibration energy of aero-engines provided in the embodiments of the present invention;

[0113] Figure 2 These are diagrams illustrating the forces and moments of the shell unit provided in this embodiment of the invention.

[0114] Figure 3 This is the acoustic intensity field of the flexural wave structure provided in the embodiments of the present invention;

[0115] Figure 4 The shear wave structure acoustic intensity field provided in this embodiment of the invention

[0116] Figure 5 The torsional wave structure acoustic field provided in this embodiment of the invention

[0117] Figure 6 The longitudinal wave structure acoustic intensity field provided in this embodiment of the invention

[0118] Figure 7 This is a three-dimensional model of the support system provided in the embodiments of the present invention.

[0119] Figure 8 The location for selecting the measuring point of the outer casing provided in this embodiment of the invention.

[0120] Figure 9 This is the first-order mode provided in the embodiments of the present invention;

[0121] Figure 10 This is the second-order mode provided in the embodiments of the present invention;

[0122] Figure 11 This refers to the location where the excitation force is applied, as provided in the embodiments of the present invention.

[0123] Figure 12 This is the response curve of applying excitation to bearing housing No. 1 provided in an embodiment of the present invention;

[0124] Figure 13 This is the response curve of applying excitation to bearing housing No. 2 provided in an embodiment of the present invention;

[0125] Figure 14 This is the response curve of applying excitation to bearing housing No. 3 provided in an embodiment of the present invention;

[0126] Figure 15 This is a time-frequency diagram of applying excitation to bearing housing No. 1 provided in an embodiment of the present invention;

[0127] Figure 16 This is a time-frequency diagram of applying excitation to bearing housing No. 2 provided in an embodiment of the present invention;

[0128] Figure 17 This is a time-frequency diagram of applying excitation to bearing housing No. 3 provided in an embodiment of the present invention;

[0129] Figure 18 This is a time-frequency diagram of applying excitation to bearing housings 1 and 2, provided in an embodiment of the present invention.

[0130] Figure 19 This is a time-frequency diagram of applying excitation to bearing housings 1 and 3, provided in an embodiment of the present invention;

[0131] Figure 20 This is a time-frequency diagram of applying excitation to bearing housings 2 and 3, provided in an embodiment of the present invention;

[0132] Figure 21 This is a time-frequency diagram of applying excitation to bearing housings 1, 2, and 3, provided in an embodiment of the present invention;

[0133] Figure 22 These are the vibration energy streamlines provided in the embodiments of the present invention;

[0134] Figure 23 This is the RNN structure provided in the embodiments of the present invention;

[0135] Figure 24 This is the LSTM structure provided in the embodiments of the present invention;

[0136] Figure 25 This is a comparison chart of the predicted data and the original data provided in the embodiments of the present invention;

[0137] Figure 26 This is the original data frequency domain diagram provided in the embodiments of the present invention;

[0138] Figure 27 This is a frequency domain diagram of the predicted data provided in an embodiment of the present invention;

[0139] Figure 28 This is the signal source tracing model provided in the embodiments of the present invention;

[0140] Figure 29 This refers to the amplitude response ratio at each point of the same excitation provided in the embodiments of the present invention;

[0141] Figure 30 It is the amplitude response ratio at different excitation points provided in the embodiments of the present invention. Detailed Implementation

[0142] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0143] This invention addresses the shortcomings of existing aero-engine vibration monitoring technologies by proposing a vibration energy tracing method based on deep learning and visualization techniques. Existing technologies suffer from insufficient accuracy, poor real-time performance, and weak visualization capabilities in studying vibration signal transmission patterns and tracing vibration signals, making it difficult to meet the needs of modern aero-engine maintenance and fault diagnosis.

[0144] First, this invention establishes a high-precision vibration model by conducting in-depth research on the vibration response transmission law of aero-engine support systems, combining theoretical analysis and numerical simulation. Compared with traditional simplified models, this method can more accurately describe the transmission law of vibration between different components and nodes, improving the accuracy and reliability of vibration monitoring.

[0145] Secondly, this invention introduces deep learning technology to predict the vibration response signal of the aero-engine support system. By constructing convolutional neural network (CNN) and recurrent neural network (RNN) models and training and optimizing them using a large amount of experimental data, high-precision prediction of vibration signals is achieved. This method overcomes the problems of weak data processing capabilities and low prediction accuracy in traditional vibration signal prediction methods, and improves the system's intelligence level and prediction ability.

[0146] Furthermore, this invention proposes a vibration signal source tracing technology. By combining a vibration transmission law model and deep learning prediction results, and utilizing signal reverse analysis technology, it accurately locates the source and propagation path of vibration signals. This method solves the problems of insufficient positioning accuracy and difficulty in accurately identifying vibration sources in traditional source tracing technologies, providing strong technical support for fault diagnosis.

[0147] Finally, this invention enables the visualization of vibration energy in aero-engines. By utilizing advanced visualization technology, the transmission and distribution of vibration energy are intuitively displayed in the form of 3D heat maps, dynamic images, and other formats. Compared to traditional text and two-dimensional chart display methods, this visualization technology greatly enhances the intuitiveness and effectiveness of information transmission, helping engineers to understand and analyze vibration conditions more quickly and improving the efficiency of fault diagnosis and maintenance.

[0148] In summary, this invention significantly improves the vibration monitoring and fault diagnosis capabilities of aero-engines through multiple technological innovations, solves several key problems in the prior art, and has high application value and broad prospects.

[0149] The working principle of the vibration energy visualization and source tracing method for supporting stator mechanical structures provided in this invention can be summarized in detail as follows:

[0150] This method aims to achieve visualized source tracing of vibration energy in aero-engine support systems through a series of steps. These steps include research on vibration response transmission laws, experimental analysis of vibration response signals, deep learning-based signal prediction, research on vibration signal source tracing techniques, and ultimately, visualization of vibration energy.

[0151] 1. Study on the vibration response transmission law of aero-engine support system (S1)

[0152] Based on the improved blind source separation algorithm: According to the simulation structure of the aero-engine support system, a blind source separation algorithm based on information theory and maximum entropy algorithm is adopted to decompose the vibration response signals of each measuring point of the casing and determine the characterization relationship between the signals.

[0153] Power flow frequency response function analysis: Based on the power flow frequency response function, the transmission law of transient / steady-state total vibration energy and vibration energy components between the bearing housing and the casing is studied.

[0154] 2. Experimental and analytical study on the transmission law of vibration response signals (S2 / S6)

[0155] Through experimental methods, vibration response signals of aero-engine support systems are collected and analyzed to verify and supplement the conclusions of theoretical research.

[0156] 3. Vibration response signal prediction based on deep learning (S3 / S7)

[0157] By utilizing deep learning techniques, such as neural network models, the vibration response signals of aero-engine support systems can be predicted, providing data support for fault diagnosis and prediction.

[0158] 4. Research on Vibration Signal Source Tracing Technology (S4 / S8)

[0159] By studying the source and propagation path of vibration signals and using signal processing techniques such as spectrum analysis and modal analysis, key features in vibration signals can be identified, providing a foundation for the visualization of vibration energy.

[0160] 5. Realize the technology for visualizing the vibration energy of aero-engines (S5)

[0161] Research on the theoretical basis of structural acoustic intensity method / vibration wave: This study investigates the propagation characteristics of structural acoustic intensity and vibration waves in aero-engine support systems, providing theoretical support for the visualization of vibration energy.

[0162] Compile trace visualization code: Develop or compile specific visualization code to draw and display vibration energy traces in the aero-engine support system, thereby enabling energy visualization.

[0163] 6. ANSYS Finite Element Analysis and Data Processing (Step 110)

[0164] A finite element model of the aero-engine support system was established using ANSYS software, and excitation loads and constraints were applied.

[0165] The dynamic solution is obtained by using a solver to extract parameters such as internal forces and velocities from the finite element model.

[0166] Using data processing tools such as MATLAB, the extracted data is processed and analyzed to calculate parameters such as structural acoustic intensity.

[0167] 7. Post-processing and visualization (Step 1115)

[0168] Post-processing software such as TECPLOT is used to read the calculated structural acoustic intensity and other parameters, and to draw visualization results such as structural acoustic intensity vector diagrams.

[0169] Save the visualization results to the specified file directory for subsequent analysis and application.

[0170] 8. Program ends (Step 16)

[0171] After completing all calculations and analyses, the program terminates and exits.

[0172] Based on the above working principle, this method can realize the visual tracing of vibration energy in the aero-engine support system, providing strong support for the design, fault diagnosis and performance optimization of aero-engines.

[0173] This invention provides a method for visualizing and tracing the vibration energy of a supporting stator mechanical structure. The technique includes:

[0174] S1: Study on the vibration response transmission law of aero-engine support system;

[0175] S2: Experimental and analytical study on the transmission law of vibration response signal in aero-engine support system;

[0176] S3: Vibration response signal prediction of aero-engine support system based on deep learning;

[0177] S4: Research on vibration signal tracing technology of a certain type of aircraft engine support system;

[0178] S5: Enables visualization technology for vibration energy of aero-engines;

[0179] S6: Experimental and analytical study on the transmission law of vibration response signal in aero-engine support system;

[0180] S7: Vibration response signal prediction of aero-engine support system based on deep learning;

[0181] Research on vibration signal tracing technology of S8 type aero-engine support system.

[0182] The working principle of the method for visualizing and tracing the source of vibration energy in a supporting stator mechanical structure.

[0183] 1. Overview

[0184] This invention relates to a visualization and source tracing method for vibration energy in aero-engines, which is mainly achieved through the study of vibration response transmission laws, deep learning prediction, vibration signal source tracing technology, and vibration energy visualization technology.

[0185] 2. Specific steps and working principle

[0186] S1: Study on the Vibration Response Transmission Law of Aero-engine Support System

[0187] Objective: To study the vibration response transmission law of aero-engine support systems in order to understand how vibration propagates in the support system.

[0188] Methods: A vibration model of the support system was established through theoretical analysis and numerical simulation to analyze the transmission law of vibration response among different components and nodes.

[0189] S2: Experimental and Analytical Study on Vibration Response Signal Transmission Law of Aero-engine Support System

[0190] Objective: To study the transmission law of vibration signals in the support system through experimental verification and analysis.

[0191] Methods: Sensors were placed on an actual aero-engine support system to measure vibration signals. The accuracy of the vibration transmission law model was verified through data analysis and spectrum analysis.

[0192] S3: Vibration Response Signal Prediction of Aero-engine Support System Based on Deep Learning

[0193] Objective: To predict the vibration response signal of a support system using deep learning algorithms.

[0194] Methods: Collect a large amount of vibration signal data, construct a deep learning model (such as convolutional neural network, recurrent neural network, etc.), train and optimize it to achieve accurate prediction of vibration response signals.

[0195] S4: Research on Vibration Signal Tracing Technology of a Certain Type of Aircraft Engine Support System

[0196] Objective: To investigate how to trace the vibration signals of a certain type of aircraft engine support system, and to identify the vibration source and propagation path.

[0197] Methods: Combining vibration transmission law models and deep learning prediction results, the source and propagation path of vibration signals are traced through signal reverse analysis technology.

[0198] S5: Achieving Visualization Technology for Vibration Energy of Aero-engines

[0199] Objective: To visualize the transmission and distribution of vibrational energy.

[0200] Methods: Based on the vibration transmission law and source tracing results, visualization technology (such as heat maps, 3D images, etc.) is used to display the distribution and transmission path of vibration energy, helping engineers to intuitively understand the vibration situation.

[0201] S6: Experimental and Analytical Study on Vibration Response Signal Transmission Law of Aero-engine Support System

[0202] Objective: To deepen our understanding of the laws governing the transmission of vibration signals through further experiments and analysis.

[0203] Methods: Repeat and expand previous experiments, collect more data for analysis, and verify and improve the vibration transmission law model.

[0204] S7: Vibration Response Signal Prediction of Aero-engine Support System Based on Deep Learning

[0205] Objective: To further optimize and apply deep learning models to improve the accuracy and robustness of vibration signal prediction.

[0206] Methods: By utilizing new experimental data and optimized deep learning algorithms, we improve the training and prediction capabilities of the model to ensure prediction accuracy under different working conditions.

[0207] Research on Vibration Signal Source Tracing Technology of S8 Type Aircraft Engine Support System

[0208] Objective: To further research and apply vibration signal tracing technology to improve its accuracy and applicability.

[0209] Methods: By combining new experimental data and optimized source tracing algorithms, the accuracy of locating the source and propagation path of vibration signals is improved, ensuring the effectiveness of source tracing technology in different engine models.

[0210] This invention achieves accurate prediction and intuitive display of vibration energy in aero-engine support systems through the comprehensive application of theoretical research, experimental verification, deep learning prediction, signal tracing, and visualization technologies. By deeply studying the transmission laws of vibration signals and combining advanced deep learning algorithms and visualization techniques, it solves the problem of accurately predicting and tracing vibration energy using traditional methods, providing an effective technical means for vibration monitoring and fault diagnosis of aero-engines.

[0211] To study the laws governing vibration energy transfer, the structural intensity method can be applied to the transient / steady-state vibration analysis of aero-engines. The structural intensity method combines the force and velocity at any point in an elastic structure to characterize the energy flow within the vibrating structure. The specific technical approach is described below. Figure 1 As shown:

[0212] This method, proposed by Noiseux et al., has been extended into a vector sound field method for energy flow in the field of structural acoustic transmission. Since the structural acoustic intensity field is a vector field, the magnitude and direction at any point in the field can predict and quantify the magnitude and direction of vibrational energy transmission at that point. Therefore, through vector field visualization, the structural acoustic intensity method can be used to describe the main transmission paths and distribution characteristics of vibrational energy in a structure. Furthermore, its divergence field can be used to indicate the sources and sinks of vibrational energy in the structure, directly analyzing and determining the main sources and dissipation locations of vibrational energy in the structure, providing vibration reduction measures from three levels: source, propagation path, and receiver. Based on this, this chapter extends the structural acoustic intensity method into a matrix form and applies it to the field of aero-engines. Using a computational system built with finite element tools and a self-compiling program, the transient and steady-state total structural acoustic intensity field of the casing, as well as the structural acoustic intensity fields of longitudinal waves, shear waves, torsional waves, and bending waves, under the excitation of unbalanced forces on high and low-pressure rotors, are solved and visualized. The transmission characteristics and distribution patterns of the transient and steady-state vibrational energy carried by these four vibration waves on the casing are analyzed. Furthermore, the intrinsic physical relationship between structural acoustic intensity and structural vibration characteristics was derived and analyzed through the equation of motion.

[0213] (1) Theory of structural acoustic intensity method

[0214] The propagation of vibration in a structure is essentially the transfer of vibration energy. The vibration load generated by the unbalanced force excitation of the rotor is essentially transferred to the casing through the support plate in the form of vibration energy. It is then transmitted in the casing and coupled with and influences the vibrations of other components.

[0215] The structural acoustic intensity method, as a power flow analysis method, considers the magnitude and phase relationship of force and velocity responses to characterize the magnitude and direction of vibrational energy transfer. The general tensor expression for transient structural acoustic intensity is:

[0216] I i (t)=-∑ j σ ij (t)v j (t)i,j=1,2,3 (1)

[0217] Where: σ ij (t) and v j (t) represent the stress tensor component and velocity vector component of the structure at time t, respectively. Equation (1) shows that the structural acoustic intensity method characterizes the vibration energy flow of the structure per unit time and unit cross-sectional area. Based on Equation (1), the stress tensor component and velocity vector component can be extracted using a self-compiled program, allowing visualization of vibration energy changes and quantitative analysis of the main transmission paths, sources, and sinks of vibration energy in the structure. Combining the finite element method and the structural acoustic intensity method allows for the analysis of abnormal vibrations and noise in engine components, helping to identify fault locations and types, which is of great significance for maintenance and fault prevention.

[0218] Vibrations propagate in structures in various wave forms, primarily including four types: longitudinal waves, shear waves, torsional waves, and bending waves. Vibrational energy is carried and transferred within the structure by these waves. On any vibrational power flow streamline, the tangent direction at a point is aligned with the power flow vector direction at that point. Since the wall thickness of an aero-engine casing structure is much smaller than its radius, shell elements (L-type) can be used for simulation. For details on the forces, moments, and displacements of a typical shell element, see [link to relevant documentation]. Figure 27 As shown.

[0219] Let these represent the translational and rotational displacements of the shell element, respectively. Substituting the forces, moments, and displacements into equation (1) and using a Fourier transform, we can obtain the frequency domain expression of the vibrational power flow per unit width of the shell element. Since the shell element is a 2D element, its vibrational power flow can be decomposed into components in the x and y directions perpendicular to the normal z in the element coordinate system. and As shown in equation (2).

[0220]

[0221] The total vibration power flow magnitude I tol It can be represented as

[0222]

[0223] In the formula, N11 and N22 are in-plane axial forces, N12 and N21 are in-plane shear forces (N12 = N21), Q13 and Q23 are transverse shear forces, M11 and M22 are bending moments, M12 and M21 are torques (M12 = M21), ux, uy and uz are translational displacements, and θx and θy are element rotational displacements. Im represents the imaginary part of the complex number.

[0224] To characterize the ratio of the vibrational energy flux transmitted through a cross section in a specific direction to the total vibrational energy passing through that cross section, the vibrational power flux ratio is defined.

[0225]

[0226] In the formula, Let be the vector of vibrational energy transmitted through a cross section in a specific direction, where n is the statistical count of vibrational energies transmitted through the cross section in that specific direction, and A is the area of ​​the cross section. The numerator represents the flux of vibrational energy through the cross section in a specific transmission direction, while the denominator represents the total vibrational energy transmitted through the cross section in that direction.

[0227] (2) Self-compiled code and environment deployment

[0228] This chapter provides a method for post-processing the model harmonic response analysis results using self-compiled APDL command-line code under Windows, importing the data results into MATLAB software for analysis, converting the file format and configuring environment variables in Windows to generate energy streamlines via Tecplot. The code framework is as follows.

[0229] Step 1: Extract stress and displacement results and calculate vibration energy.

[0230] / POST1 ! Entering post-processing mode

[0231] ! Stress extraction results

[0232] *GET,NODE_COUNT,NODE,0,COUNT! Get the total number of nodes.

[0233] *GET,ELEM_COUNT,ELEM,0,COUNT! Get the total number of cells.

[0234] Create an array to store stress results.

[0235] DIM,STRESS_ARRAY,ARRAY,NODE_COUNT,6

[0236] Loop through all nodes and extract the stress results.

[0237] DO I = 1, NODE_COUNT

[0238] *GET,NODE_I,X,NODE,I,LOC! Get node coordinates

[0239] *GET,NODE_I,SELN,NODE,I,S,X! (Get nodal stress results)

[0240] STRESS_ARRAY(I, 1) = NODE_I(2)! X-direction stress

[0241] STRESS_ARRAY(I,2)=NODE_I(3)!Y-direction stress

[0242] STRESS_ARRAY(I,3)=NODE_I(4)!Z-direction stress

[0243] STRESS_ARRAY(I,4)=NODE_I(5)!XY Shear Stress

[0244] STRESS_ARRAY(I, 5) = NODE_I(6)! XZ Shear Stress

[0245] STRESS_ARRAY(I, 6) = NODE_I(7)! YZ Shear stress

[0246] ENDDO

[0247] ! Extract displacement results

[0248] *GET, U_COUNT, NODE, 0, COUNT, U, X! (Get displacement result)

[0249] Create an array to store the displacement results.

[0250] DIM,DISPLACEMENT_ARRAY,ARRAY,NODE_COUNT,3

[0251] Loop through all nodes and extract the displacement results.

[0252] DO I = 1, NODE_COUNT

[0253] *GET,U_I,X,NODE,I,U,X! Get the displacement of a node in the X direction.

[0254] *GET,U_I,Y,NODE,I,U,Y! Get the displacement of a node in the Y direction.

[0255] *GET,U_I,Z,NODE,I,U,Z! Get the Z-direction displacement of a node.

[0256] DISPLACEMENT_ARRAY(I, 1) = U_I(2)! Displacement in the X direction

[0257] DISPLACEMENT_ARRAY(I,2)=U_I(3)!Y-direction displacement

[0258] DISPLACEMENT_ARRAY(I,3)=U_I(4)!Z-direction displacement

[0259] ENDDO

[0260] ! Calculate vibrational energy

[0261] DIM,VIBRATION_ENERGY,ARRAY,NODE_COUNT

[0262] DO I = 1, NODE_COUNT

[0263] VIBRATION_ENERGY(I)=(STRESS_ARRAY(I,1)2+STRESS_ARRAY(I,2)2+STRESS_ARRAY(I,3)2) / 2+(DISPLACEMENT_ARRAY(I,1)2+DISPLACEMENT_ARRAY(I,2)2+DISPLACEMENT_ARRAY(I,3)2) / 2

[0264] ENDDO

[0265] Step 2: Visualize the vibration energy distribution

[0266] / POST26! Enter vibration energy post-processing mode

[0267] Visualizing the distribution of vibrational energy on the model.

[0268] *VWRITE,VIBRATION_ENERGY! Writes vibrational energy into the variable.

[0269] PLNSOL,S! Draw contour maps on a plane.

[0270] Step 3: Unfold the 3D solid model into a plane.

[0271] / PREP7! Enter preparation mode

[0272] Unfold the 3D solid model into a plane.

[0273] *GET,MIN_X,ELEM,1,AREA,XMIN! Get the minimum X-coordinate of the model.

[0274] *GET,MAX_X,ELEM,1,AREA,XMAX! Get the maximum X-coordinate of the model.

[0275] *GET,MIN_Y,ELEM,1,AREA,YMIN! Get the minimum Y-coordinate of the model.

[0276] *GET,MAX_Y,ELEM,1,AREA,YMAX! Get the maximum Y-coordinate of the model.

[0277] Create a plane

[0278] LSEL,S,ELEM! Select all cells

[0279] *GET,ELEM_COUNT,ELIST! Get the number of cells.

[0280] ETABLE, LST, AREA, ALL! Unfold all elements onto the plane.

[0281] PLNSOL, ALL! Draw contour maps on a plane.

[0282] Step 4: Mark the trajectory of vibrational energy flow.

[0283] / POST26! Entering vibration energy post-processing mode

[0284] Mark the trajectory of vibrational energy flow on the plane and use arrows to indicate the direction and magnitude.

[0285] PLNSOL,VIBRATION_ENERGY! Draw contour maps on a plane.

[0286] PLVECT,VIBRATION_ENERGY! (Drawing vector graphics on a flat surface)

[0287] / DEVICE,PNG,SAVE,DESKTOP\flow.png! Save the planar diagram showing the energy flow trajectory to your computer desktop.

[0288] To ensure the accuracy of the programmed calculation results, this chapter establishes a communication mechanism between MATLAB and ANSYS APDL software. The model vibration energy simulation results are extracted from ANSYS and imported into MATLAB for visualization of the vibration energy transfer path.

[0289] APDL calls MATLAB command streams:

[0290]

[0291] MATLAB calling APDL scripting language:

[0292] %creat flag for ANSYS call MATLAB%

[0293] FLAG = zeros(1, 1);

[0294] FLAG(1,1)=0

[0295] Fid2=fopen('FLAG.TXT','w');

[0296] While fid2==1

[0297] Fid2=fopen('FLAG.TXT','w');

[0298] End

[0299] Fprintf(fid2,'%f\t',FLAG(1,1));

[0300] St2 = fclose(fid2);

[0301] While st2==1

[0302] St2 = fclose(fid2);

[0303] End

[0304] %close matlab&call for ANSYS%

[0305] Exit

[0306] (3) Calculation Results and Verification

[0307] This section uses the aforementioned calculation system to solve for the total structural acoustic field of the casing in both transient and steady states, as well as the single-point excitation of the structural acoustic fields of longitudinal waves, shear waves, torsional waves, and bending waves under the excitation of unbalanced forces from high and low pressure rotors. The transmission characteristics and distribution patterns of the transient and steady-state vibration energy carried by these four types of vibration waves on the casing are analyzed. Furthermore, the intrinsic physical relationship between structural acoustic intensity and structural vibration characteristics is derived and analyzed through the equations of motion.

[0308] To more directly and clearly demonstrate the structural acoustic intensity field of different vibration waves on the casing, the self-compiled program unfolds the casing circumferentially into a two-dimensional plane, and the resulting coordinate system and corresponding output data vectors are also modified accordingly. Figure 3 As shown.

[0309] Unfold the casing model circumferentially. Figure 3 Observing in the indicated direction, and referring to the relative positions of each component in the actual model, the straight line corresponding to the end position x=200 is the flange edge. A sinusoidal excitation with a frequency of 20 Hz and a magnitude of 60 N is applied to (100, 50), obtaining the circumferentially expanding vibration wave structural acoustic field. A shear wave with a direction of 45 degrees and a scale of 2 is applied to this component model, and the keyframe structural acoustic field at 20 seconds is captured as follows. Figure 4 As shown. A torsional wave with an angular velocity of 2 rad / s and a radius of 10 mm is generated. The keyframe acoustic field at 20 s is shown below. Figure 5 As shown. A longitudinal wave with a wavelength of 0.5 mm and a velocity of 1 mm / s is applied, and the keyframe structural acoustic field at 20 s is captured as follows. Figure 6 As shown.

[0310] Most of the vibration energy on the casing is carried and transmitted by longitudinal waves, bending waves, and shear waves, while torsional waves transmit the smallest proportion of vibration energy. The casing flange hinders the transmission of longitudinal wave vibration energy, effectively cutting off its transmission and concentrating the vibration energy carried by the longitudinal waves on the vibrating source and the vibrating casing nearby. Conversely, the vibration energy carried by shear waves and torsional waves can freely pass through the flange without changing its transmission direction. Therefore, shear waves in the casing are more likely to cause overall vibration of the aero-engine. The vibration energy transmitted along the main path on the casing is not carried by a single type of vibration wave throughout the entire transmission process, but rather involves the mutual conversion and transmission of different types of vibration waves. Bending wave vibration energy is mainly distributed near the casing at the connection with the support plate, offset from the energy distribution positions of shear waves, and is the source of the main transmission path of vibration energy on the casing. Therefore, dissipating the bending wave vibration energy at this location can effectively block the transmission of vibration energy and reduce vibration noise during aero-engine operation. The steady-state structural acoustic field reflects the average distribution law and transmission characteristics of vibration energy within a vibration response cycle. Bending wave vibration energy serves as the source of casing vibration energy, with steady-state peak values ​​comparable to transient peak values. Steady-state structural acoustic intensity is a complex vector product of force and displacement (velocity); therefore, a single amplitude (velocity) distribution cannot pinpoint or display information such as the casing's vibration source, vibration convergence point, and main vibration propagation path. The structural acoustic intensity method analyzes structural vibration problems from the perspective of energy transfer. Therefore, it establishes an intrinsic physical connection between energy parameters such as kinetic energy, strain energy, and damping dissipation and structural vibration characteristics. Vibration control of a structure essentially involves controlling the vibration energy flow at three levels: the vibration source, the transmission path, and the vibration convergence point, by reducing vibration excitation energy, blocking or altering the vibration energy transmission path, and enhancing vibration energy dissipation.

[0311] Application Scenario 1: Experimental and analytical study on the transmission law of vibration response signal in aero-engine support system

[0312] The internal structure of an aero-engine is complex and difficult to disassemble. The high-temperature environment inside the engine is extremely detrimental to sensor operation; therefore, when the engine is running, the sensor vibration measurement point is typically selected on the external casing. Before reaching the casing, the vibration signal undergoes multiple transmission paths and is modulated in various ways. These vibration responses couple to form a complex vibration response on the casing. Therefore, obtaining the vibration transmission characteristics of the aero-engine support system through casing vibration signals is crucial. Vibration energy visualization technology plays a vital role in this process. This technology can convert complex vibration signals into intuitive graphics or images, helping engineers and technicians more easily understand the transmission characteristics and dynamic responses of vibration signals. Through visualization, abnormal or atypical behaviors in the vibration source and transmission path can be more clearly identified, thereby enabling more effective fault diagnosis and system maintenance. Furthermore, vibration energy visualization can help optimize sensor layout and adjustment, ensuring the acquisition of the most accurate and useful vibration data to improve the monitoring and maintenance efficiency of the entire aero-engine support system.

[0313] (1) Harmonic response analysis of the aircraft engine support system model

[0314] Establish a simplified three-dimensional model of the support system, such as Figure 7 The bearing housings (from left to right: bearing housing 1, bearing housing 2, and bearing housing 3) are meshed using a 5mm tetrahedral mesh, while the casing and support plate are meshed using a 2mm hexahedral mesh. The total number of nodes is 677,773, and the total number of elements is 140,944.

[0315] Vibration measuring point location selection as follows Figure 8 As shown.

[0316] The bearing housing bottom surface was set as a fixed support, and the first 10 modes of the calculated system are shown in Table 3. Harmonic response analysis was performed using the modal superposition method, with the first 10 modes set for calculation. Figure 9 and Figure 10 These are the first two modes of the model.

[0317] Table 3 First 10 Modes of the Support System

[0318]

[0319]

[0320] Apply a sinusoidal excitation to the side of the bearing housing, such as Figure 11 As shown, the values ​​are 100N, 200N, and 300N respectively. The solution frequency range is set to 0–600Hz, the load step interval is 5Hz, and there are a total of 120 steps.

[0321] The amplitude-frequency response curve of the outer casing obtained by applying excitation to bearing housing No. 1 is as follows: Figure 12 As shown.

[0322] The amplitude-frequency response curve of the outer casing obtained by applying excitation to bearing housing No. 2 is as follows: Figure 13 As shown.

[0323] The amplitude-frequency response curve of the outer casing obtained by applying excitation to bearing housing No. 3 is as follows: Figure 14 As shown:

[0324] Based on the modal analysis results, when a sinusoidal excitation is applied to the support system, the deformation occurring at resonance is mainly in the outer casing. The calculated amplitude-frequency response curves show peak values ​​around 90Hz, 120Hz, 240Hz, and 350Hz, which is consistent with the natural frequencies calculated by the modal analysis. Particularly, the outer casing response exhibits its maximum peak value around 350Hz. The amplitude-frequency response curves obtained by applying excitation to the three bearing housings show roughly the same trend at the same measuring point. The peak values ​​of the frequency response curves obtained by applying excitation to bearing housings 1 and 3 are similar, while the peak value of the frequency response curve obtained by applying excitation to bearing housing 2 is significantly higher than the other two. When applying excitation to the same bearing housing, the greater the applied sinusoidal force, the larger the peak value of the response. The response amplitude at the measuring points on the casing edge (measuring points 1 and 3) is larger than that at the middle measuring points (measuring points 2 and 4).

[0325] (2) Transient response analysis of the aircraft engine support system model

[0326] Transient response analysis is used to analyze the displacement and strain of a structure under load changes over time. Through transient analysis, the response of the outer casing at different frequencies over time can be obtained. The solution time step is set to 0.01s, the solution time is 10s, and a total of 1000 steps are performed. A sinusoidal excitation of 200N is applied to the bearing housing. A sinusoidal excitation of 50Hz is applied to different bearing housings.

[0327] An excitation force is applied to bearing housing No. 1, and the time-domain plot and spectrum plot of the measuring point on the outer casing are as follows: Figure 15 As shown.

[0328] An excitation force was applied to bearing housing No. 2, and the time-domain plot and spectrum of the measuring point on the outer casing are as follows: Figure 16 As shown.

[0329] An excitation force was applied to bearing housing No. 3, and the time-domain plot and spectrum plot of the measuring point on the outer casing are as follows: Figure 17 As shown.

[0330] Excitation forces were applied to bearing housings 1 and 2 at frequencies of 50 Hz and 100 Hz, respectively. The time-domain diagram and spectrum diagram of the measuring point on the outer casing are shown in Figure 18.

[0331] Excitation forces were applied to bearing housings 1 and 3 at frequencies of 50Hz and 100Hz, respectively. The time-domain plot and spectrum of the measuring points on the outer casing are shown below. Figure 19 As shown.

[0332] Excitation forces were applied to bearing housings 2 and 3 at frequencies of 50Hz and 100Hz, respectively. The time-domain plot and spectrum of the measuring point on the outer casing are shown below. Figure 20 As shown.

[0333] A 200N excitation was applied to the three bearing housings at frequencies of 50Hz, 100Hz, and 150Hz, respectively. The time-domain and frequency spectrum diagrams of the measurement points on the outer casing are shown below. Figure 21 As shown.

[0334] Transient response analysis reveals that the amplitude at the outer casing measurement point varies periodically with time. Fourier transform yields the spectrum of the outer casing response measurement point. Under single-point excitation, a peak is observed at 49.5Hz in the spectrum, which is consistent with the calculated 50Hz excitation. The peak value is largest when excitation is applied to bearing housing 2. Under multi-point excitation, peaks also appear near the given excitation frequency in the frequency domain.

[0335] Application Scenario 2: Vibration Response Signal Prediction of Aero-engine Support System Based on Deep Learning

[0336] LSTM models in deep learning, with their excellent long-term memory capabilities and powerful modeling ability for time-series data, have shown great potential in the field of aero-engine fault diagnosis. By using LSTM models to model and predict time-series data, the operating status of engines can be assessed more accurately, engine health can be monitored in real time, and faults can be predicted, allowing for timely maintenance and repair measures to ensure flight safety and normal flight operations. Furthermore, combined with vibration energy visualization technology, the prediction results of LSTM models can be displayed intuitively, making it easier for maintenance personnel to identify and interpret complex vibration signals, further improving the understanding of engine status and the accuracy of fault prediction. However, existing LSTM models face certain challenges when dealing with time-series data containing missing signals. The presence of missing values ​​can interfere with the model's learning process and reduce its predictive performance. Therefore, researching how to effectively utilize LSTM models to predict aero-engine sensor data containing missing signals, and enhancing the expression and application of these predictions through vibration energy visualization technology, is of great significance for improving the accuracy and robustness of aero-engine fault diagnosis.

[0337] (1) Basic Model

[0338] RNN stands for Recurrent Neural Networks, used to process sequential data. In traditional neural network models, layers from the input layer to the hidden layer and then to the output layer are fully connected, but nodes within each layer are unconnected. However, this type of ordinary neural network is ineffective for many time series problems. For example, to predict the next word in a sentence, you generally need to use the preceding words because words in a sentence are not independent. RNNs are called recurrent neural networks because the current output of a sequence is related to the outputs of previous steps. Specifically, the network memorizes information from previous time steps and applies it to the calculation of the current output. That is, nodes in the hidden layers are no longer unconnected but connected, and the input of the hidden layer includes not only the output of the input layer but also the output of the hidden layer from the previous time step.

[0339] In RNNs, sequential data is input into the network in chronological order, and each time step corresponds to a hidden state. These hidden states constitute the intermediate representation of the network at different time steps. Hidden states play a crucial role in RNNs. They carry the information of the sequential data by connecting the neurons of each hidden layer, and transmit and update this information between different time steps. Specifically, in a simple RNN structure, the hidden state is updated at each time step to reflect the input data of the current time step and the hidden state of the previous time step. For example, in the first layer, at time step t, the neurons of the RNN hidden layer will obtain the hidden state ht[1], and at time step t+1, they will receive the hidden state ht[1] from the previous time step and calculate the new hidden state ht+1[1]. In this way, the transmission of hidden states between different time steps forms the continuous processing of sequential data. In addition, from the vertical direction, different layers are also connected through hidden states. On the horizontal timeline, the hidden state at each time step connects to the hidden state of the same level at the next time step. Vertically, hidden states at different levels also influence each other through specific connections. This inter-layer connection method gives the RNN model vertical scalability, enabling it to handle deeper feature representations and abstractions. In summary, an RNN is a structure that can scale both horizontally and vertically, achieving effective modeling and processing of sequential data through the propagation and updating of hidden states. While horizontal scalability is less common in practical applications, the hierarchical connections and hidden state propagation in the vertical direction are the key mechanisms enabling RNN models to handle long sequence data and learn complex feature representations. The RNN network structure is as follows: Figure 23 As shown.

[0340] LSTM (Long Short-Term Memory) is a special type of recurrent neural network, differing from traditional feedforward neural networks. In feedforward neural networks, the input at each time step is considered completely independent of the input at the next time step. This is reasonable for some tasks (such as image classification), but for tasks involving time series (such as natural language processing or continuous data analysis), it is crucial to make reasonable use of past information to analyze the input at the current time step. Recurrent Neural Networks (RNNs) are designed to address this need. Simply put, RNNs allow the network to make reasonable use of previous input information when processing the current input. Its structure allows information to be passed from one time step to the next, enabling the network to model sequential data. For example, when processing natural language text, understanding the meaning of a word requires considering previously encountered words. In this case, RNNs can effectively capture contextual information in the text, not just information about individual words. LSTM, as a special form of RNN, further improves the structure of RNNs by introducing gating mechanisms, enabling it to better handle long-term dependencies and prevent gradient vanishing or exploding problems. This makes LSTM perform better when processing time series data, especially in tasks involving long-term memory, such as language modeling and machine translation. Therefore, LSTM has become a powerful tool for processing time series data and has been widely used in natural language processing, continuous data analysis, and other fields. The LSTM model is as follows: Figure 24 As shown.

[0341] In LSTM, one of the key elements is the cell state, a crucial component of the LSTM network that runs throughout the entire network and carries the network's memory and summary of the input data. The cell state can be simply understood as the LSTM's memory of the input data, updated and adjusted at each time step to reflect the network's understanding and summary of past input information. In LSTM, the updating and propagation of the cell state are achieved through a series of gating mechanisms. These gating mechanisms control the flow and forgetting of information, effectively handling long sequences of data and preventing gradient vanishing or exploding problems. Symbolically, the cell state can be represented by Ct, representing the memory after passing through the LSTM cell at time t. This vector contains a summary of all input information from the LSTM, capturing long-term dependencies in the sequence data and propagating and updating it across different time steps, enabling the network to better understand and predict patterns and regularities in the sequence data. In summary, the cell state is one of the core elements of the LSTM network, allowing the network to effectively capture and utilize long-term dependencies in sequence data, thus performing exceptionally well in processing time series data, especially in tasks involving long memory and long sequences.

[0342] In LSTM, there are three important gating mechanisms: forget gate, input gate, and output gate. They are responsible for controlling the updating and adjustment of the LSTM cell state, so as to effectively process time series data and prevent gradient vanishing or gradient exploding problems.

[0343] Forget Gate: The forget gate selectively forgets some information from previous time steps based on the current input and the output of the previous time step. Specifically, the forget gate first combines the current input and the output of the previous time step into a vector, and then uses a sigmoid activation function to compress each component of this vector into the interval (0, 1). Thus, if a component is close to 0 after passing through the sigmoid function, it means that the information at that position will be forgotten; if it is close to 1, then that information is retained.

[0344] Input Gate: The input gate controls how the current input information is added to the cell state. First, the current input is integrated, and the effective information is extracted using the tanh function. Then, the weights of this information are controlled using the sigmoid function. These two steps together achieve the function of extracting effective information from the current input and determining which information to add to the cell state based on the weights.

[0345] Output Gate: The output gate is responsible for calculating the output value at the current time step. It maps the current cell state to the interval (1, 1) using the tanh function, then integrates the current input with the output of the previous time step, and extracts information from it using the sigmoid function. This information is multiplied by the tanh-processed cell state to obtain the final output value.

[0346] (2) Experiment and Data Analysis

[0347] This experiment analyzes three accelerometers located at three positions: the low-pressure rotor end, the middle of the outer casing, and the high-pressure rotor end of the outer casing. The sampling frequency is 1024Hz, with 23369 sampling points. The maximum and minimum values ​​are 0.265318g. Column A represents the signal acquired at the low-pressure rotor end, column B represents the signal acquired at the middle of the outer casing, and column C represents the signal acquired at the high-pressure rotor end. Assuming a 1-second data gap at point B in the middle of the outer casing after 21 seconds of operation, an LSTM model is used to predict the 1168 data points. In the time domain plot, the results with time_step=5 and time_step=5000 are compared, and the more consistent prediction results are displayed. The following figure shows the time domain plot of the test set and prediction results, where the orange curve represents the prediction result and the blue curve represents the actual vibration signal at point B. Figure 25The prediction results have been successfully made to be consistent with the test set in the time domain plot.

[0348] In the image below, blue represents the original data points, and orange represents the predicted data points.

[0349] The predicted time-domain data is processed using a Fast Fourier Transform to obtain a frequency domain graph, which is then compared with the frequency domain graph of the original signal (test set) measured at point B. Figure 26 , Figure 27 .

[0350] Based on the above experiments, it can be concluded that the vibration signal prediction value under the LSTM model is relatively accurate and stable.

[0351] 1.4 Technical Application Scenarios: Research on Vibration Signal Tracing Technology for a Certain Type of Aircraft Engine Support System

[0352] To address the energy dispersion caused by discontinuous support structures, this paper proposes a new vibration signal separation and identification method by extending the signal feature enhancement method based on geometric peak modification, starting from the geometric modification of the signal. Furthermore, considering the similarities and differences in excitation signals from different parts, the paper explores the rank and sparsity characteristics of vibration signals, proposes a novel separation and identification framework, and finally obtains the mapping relationship between the excitation source and the response of the casing measuring point.

[0353] For a certain type of engine support system, using the excitation signal and the vibration response model of the casing, the transient / steady-state total vibration energy and energy components of the support system are obtained through the Lagrangian method. Combined with the power flow frequency response function, the energy transfer path between multiple bearing seats and the casing is studied. Subsequently, the proposed synchronous oscillation source tracing method is further extended, fully considering the design scenarios for specific models and engineering realities. For scenarios where subsynchronous oscillations in actual systems have multiple inducing conditions, a support system source tracing model based on a multi-source domain adaptive algorithm is established. Figure 28 As shown in the figure, a subsynchronous oscillation source tracing method that is effective under multiple inducing conditions is proposed.

[0354] Finally, based on open-loop mode resonance theory, an excitation source inversion method in the equivalent system is proposed. Combining the mapping relationship dataset between excitation signal and response signal, a synchronous oscillation source tracing model based on multi-source domain adaptive network is established, and a casing vibration source tracing method under single / multi-point excitation conditions is developed.

[0355] Vibration energy visualization technology plays a central role in this series of methods. By converting complex vibration data into intuitive visual charts, technicians can more accurately track the energy transfer paths and distribution. This visualization not only helps identify and analyze vibration sources and transfer paths but also effectively monitors and adjusts signal processing methods to improve the accuracy of identification and analysis. Through intuitive graphical displays, vibration energy visualization technology greatly enhances engineers' understanding and control of complex system dynamics, thereby driving more efficient and accurate fault diagnosis and system optimization.

[0356] (1) Establishment of the first-generation vibration response source dictionary

[0357] The excitation F = 20000 N / 100 Hz was applied to bearing housings 1 / 2, 2 / 3, and 1 / 3 respectively. The average amplitude of the vibration response at four observation points A, B, C, and D under the same excitation was observed, and the amplitude response ratio of different bearing housings at each point was calculated. The calculation results are as follows: Figure 29 As shown.

[0358] Calculate the proportion of each of the four response observation points A, B, C, and D under different stimuli. The calculation results are as follows: Figure 30 As shown.

[0359] (2) First-generation vibration response source dictionary evaluation method

[0360] The dictionary evaluates vibration sources from both horizontal and vertical perspectives, effectively improving the accuracy of the judgment.

[0361] Lateral evaluation process: When the excitation source is in bearing housing No. 3, the response amplitude of each measuring point is the largest; when the excitation source is in bearing housing No. 2, the response amplitude of each measuring point is the second largest; when the excitation source is in bearing housing No. 1, the response amplitude of each measuring point is the smallest.

[0362] Longitudinal evaluation process: When the excitation source is in bearing housing 1, the response amplitude of measuring point A is the largest and the response amplitude of measuring point C is the smallest; when the excitation source is in bearing housing 2, the response amplitude of measuring point D is the largest and the response amplitude of measuring point B is the smallest; when the excitation source is in bearing housing 3, the response amplitude of measuring point D is the largest and the response amplitude of measuring point C is the smallest.

[0363] (3) Prospect of the method for establishing the Nth generation vibration response source dictionary

[0364] Due to time constraints, the team will optimize and upgrade the first-generation vibration response tracing dictionary in the future. This will involve analyzing the spectral characteristics of vibration signal monitoring points from the time-domain diagram, spectrum diagram, and envelope spectrum diagram of the vibration signal, thereby improving the accuracy and effectiveness of the vibration tracing method.

[0365] Example 1: Vibration Signal Tracing and Visualization Analysis of Aero-engine Support System

[0366] 1. Overview

[0367] This embodiment focuses on the source tracing and visualization analysis of vibration signals in a support system for a certain type of aircraft engine.

[0368] 2. Specific steps

[0369] S1: Study on the Vibration Response Transmission Law of Aero-engine Support System

[0370] A vibration model of the support system is established using finite element analysis software (such as ANSYS).

[0371] Simulate vibration transmission under different working conditions and analyze the transmission law of vibration between various components of the support system.

[0372] S2: Experimental and Analytical Study on Vibration Response Signal Transmission Law of Aero-engine Support System

[0373] Acceleration sensors are placed at key locations on the engine support system.

[0374] The engine is run and vibration signals are collected. The vibration data is recorded through a data acquisition system.

[0375] Use spectrum analysis tools (such as MATLAB) to analyze vibration signals and verify the accuracy of the numerical model.

[0376] S3: Vibration Response Signal Prediction of Aero-engine Support System Based on Deep Learning

[0377] A large amount of vibration signal data was collected and preprocessed to serve as the training dataset.

[0378] A vibration signal prediction model is built using a convolutional neural network (CNN), and the model is trained and optimized.

[0379] The model's predictive accuracy was verified using a test dataset.

[0380] S4: Research on Vibration Signal Tracing Technology of a Certain Type of Aircraft Engine Support System

[0381] Combining the aforementioned vibration transmission laws and deep learning models, the source and propagation path of vibration signals are traced through reverse analysis technology.

[0382] The location of the key vibration source was determined using time-frequency analysis.

[0383] S5: Achieving Visualization Technology for Vibration Energy of Aero-engines

[0384] Vibration energy can be visualized using visualization software (such as Paraview).

[0385] Generate 3D thermal images to visually display the distribution and transmission path of vibration energy, helping engineers understand vibration conditions.

[0386] Example 2: Vibration Monitoring and Fault Diagnosis of Aircraft Engine Support System

[0387] 1. Overview

[0388] This embodiment focuses on vibration monitoring and fault diagnosis of a certain type of aircraft engine support system.

[0389] 2. Specific steps

[0390] S1: Study on the Vibration Response Transmission Law of Aero-engine Support System

[0391] A physical model of the support system was established, and vibration transmission under different working conditions was simulated using a vibration test bench.

[0392] By combining analytical methods and numerical simulations, the transmission paths and patterns of vibration between different components are analyzed.

[0393] S2: Experimental and Analytical Study on Vibration Response Signal Transmission Law of Aero-engine Support System

[0394] Acceleration and displacement sensors are installed at different parts of the engine to collect vibration signals under different operating conditions.

[0395] The transmission characteristics of vibration signals between different parts were studied using spectral analysis and time-domain analysis methods.

[0396] S3: Vibration Response Signal Prediction of Aero-engine Support System Based on Deep Learning

[0397] A large amount of experimental data was collected, preprocessed, and used as input data for deep learning models.

[0398] A recurrent neural network (RNN) model is constructed, trained, and validated to predict vibration response signals.

[0399] S4: Research on Vibration Signal Tracing Technology of a Certain Type of Aircraft Engine Support System

[0400] By analyzing experimental data and prediction results from deep learning models, the source and propagation path of vibration signals can be determined.

[0401] Time-frequency analysis techniques such as wavelet transform are used to accurately locate the source of the fault.

[0402] S5: Achieving Visualization Technology for Vibration Energy of Aero-engines

[0403] Using graphics processing software, the distribution of vibration energy is visualized in three dimensions.

[0404] Generate dynamic heat maps to display changes in vibration energy in real time, helping engineers to detect potential faults in a timely manner.

[0405] S6: Experimental and Analytical Study on Vibration Response Signal Transmission Law of Aero-engine Support System

[0406] Further experimental verification and analysis will be conducted to collect more data for model optimization and improve the vibration transmission law model.

[0407] S7: Vibration Response Signal Prediction of Aero-engine Support System Based on Deep Learning

[0408] By utilizing the newly acquired experimental data, we can further train and optimize the deep learning model to improve prediction accuracy.

[0409] Research on Vibration Signal Source Tracing Technology of S8 Type Aircraft Engine Support System

[0410] By combining new experimental data and optimized source tracing algorithms, the accuracy of locating the source and propagation path of vibration signals is improved, ensuring the effectiveness of source tracing technology in different engine models.

[0411] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for visualizing and tracing the source of vibration energy in a supporting stator mechanical structure, characterized in that, The method includes: Step 1. Input and define material properties and finite element types through the material and element interface; Step 2. Input the geometric parameters of the research object through the structural model command interface and create a geometric model; Step 3. Input the material properties, element types, and geometric models generated in Steps 1 and 2 into the ANSYS preprocessing module to create a finite element model of the research object; Step 4. Input the load properties and application location through the load condition command interface to apply the excitation load to the finite element model created in Step 3; Step 5. Apply constraints to the finite element model created in Step 3 by inputting the constraint type and application location through the boundary condition command interface; Step 6. Enter the ANSYS solver module, input the dynamic solution type and related settings parameters through the solver settings command interface, and then perform the solution; Step 7. Enter the ANSYS post-processing module, input the analysis time, data extraction location, data type, and data output save location through the post-processing setting command interface, and extract the internal force and velocity parameters from the finite element model of the research object, and save the output to the file system; The method for visual analysis of vibration energy in aero-engine support systems includes the following steps: The calculation result file and element node relationship file output by ANSYS are read from the file system and organized into a matrix and stored in the workspace. MATLAB is used to read the element coordinate system, nodal coordinate system, and result coordinate system of the finite element model, and to perform the conversion between physical space and computational space. Construct the computational domain for the structural acoustic intensity vector field; Based on the relevant calculation formulas, the structural acoustic intensity vector of each element is solved in the computational domain, and the results are written into a matrix according to the relationship between the element nodes. Output the structural acoustic intensity calculation results and save them to the file system; For the transient structural acoustic intensity vector field, repeat the above steps until all analysis time points have been processed; The constructed computational domain was read using the post-processing software TECPLOT, and the structural acoustic intensity calculation result file was read to draw the structural acoustic intensity vector diagram. Save the drawn structural sound intensity vector map to the specified file directory; Step 1 includes: (a) Based on the simulation structure of the aero-engine support system, an improved blind source separation algorithm is developed using information theory and the maximum entropy algorithm to decompose the vibration response signals of each measuring point of the casing and determine the characterization relationship between the signals; (b) Combining the power flow frequency response function, we will study in detail the transmission law of transient and steady-state total vibration energy and vibration energy components between the bearing housing and the casing; (c) Conduct basic research on structural acoustic intensity method and vibration wave theory to provide theoretical support for the visualization of vibration energy; (d) Compile the trace visualization code to achieve a visual representation of the energy trace; Step 2 includes: (a) Focusing on the vibration transmission problem of the aero-engine support system, the excitation-response mapping relationship is analyzed in depth using the obtained casing vibration response signal; (b) Establish a simplified finite element model of the support system and perform mesh generation to simulate the actual structure; (c) Through single-point excitation and multi-point excitation experiments, the transient vibration signal of the response measurement point is analyzed at a constant frequency to reveal the transmission law of vibration response.

2. The method for visualizing and tracing the vibration energy of a supporting stator mechanical structure as described in claim 1, characterized in that, Step 3 includes: (a) Based on the dynamic model of the aero-engine support system, the LSTM model is used to perform time series modeling and prediction of the casing vibration response signal; (b) Accurate prediction of time-domain vibration signals is achieved by acquiring and training the vibration signals from three sampling points of the outer casing of the dual-rotor system; (c) Perform a Fast Fourier Transform on the predicted time-domain signal to obtain accurate predictions of spectral characteristics, providing support for the health management of aero-engines.

3. The method for visualizing and tracing the vibration energy of a supporting stator mechanical structure as described in claim 1, characterized in that, Step 7 includes: (a) To address the energy dispersion problem caused by discontinuous support structures, a signal feature enhancement method based on geometric peak modification is proposed to improve the accuracy of vibration signal separation and identification; (b) To address the subsynchronous oscillation problem under multi-source induced conditions, a support system source tracing model based on a multi-source domain adaptive algorithm is established, and an effective subsynchronous oscillation source tracing method is proposed. (c) Based on the open-loop mode resonance theory, an excitation source inversion method is developed in the equivalent system. Combined with the mapping relationship dataset between the excitation signal and the response signal, a synchronous oscillation source tracing model of multi-source domain adaptive network is constructed to realize the source tracing of casing vibration under single / multi-point excitation conditions.

4. A system for visualizing and tracing the source of vibration energy in an aero-engine support system based on the method of claim 1, characterized in that, The system includes: A vibration signal decomposition module is used to decompose the vibration response signals of each measuring point of the casing and determine the characterization relationship between the signals based on the simulation structure of the aero-engine support system and the blind source separation algorithm developed using information theory and maximum entropy algorithm. A vibration energy transfer analysis module is used to study the transmission law of transient and steady-state total vibration energy and vibration energy components between the bearing housing and the casing by combining the power flow frequency response function; A trace visualization module is used to compile trace visualization code to realize the visual representation of energy traces; A data storage module for storing processed vibration response signals and energy trace data.

5. A system for studying vibration transmission in an aero-engine support system based on the method of claim 1, characterized in that, The system includes: A finite element model building module is used to establish a simplified finite element model of the support system and perform mesh generation for the vibration transmission problem of the aero-engine support system. An excitation-response analysis module is used to analyze the excitation-response mapping relationship in depth using the obtained casing vibration response signal, and to reveal the transmission law of vibration response; An experimental simulation module is used to analyze the transient vibration signals of the response measurement points under single-point excitation and multi-point excitation at a constant frequency. A data output module is used to output the analysis results of the vibration transmission law.

6. A system for predicting vibration signals and analyzing spectral characteristics of an aero-engine support system based on the method of claim 1, characterized in that, The system includes: A time series modeling module is used to perform time series modeling and prediction of casing vibration response signals based on the dynamic model of the aero-engine support system and the LSTM model. A vibration signal prediction module is used to accurately predict time-domain vibration signals by acquiring and training vibration signals from three sampling points in the outer casing of a dual-rotor system. A spectral feature analysis module is used to perform a fast Fourier transform on the predicted time-domain signal to obtain accurate predictions of spectral features. A health management support module for using prediction and analysis results for the health management of aero engines.

7. A system for vibration tracing of an aero-engine support system based on the method of claim 1, characterized in that, The system includes: A signal feature enhancement module is proposed to address the energy dispersion problem caused by discontinuities in the support structure. A signal feature enhancement method based on geometric peak modification is proposed to improve the accuracy of vibration signal separation and identification. A subsynchronous oscillation tracing module is used to establish a support system tracing model based on a multi-source domain adaptive algorithm for subsynchronous oscillation under multi-source induced conditions, and to propose an effective subsynchronous oscillation tracing method. An excitation source inversion module is used to perform excitation source inversion in an equivalent system based on open-loop mode resonance theory, and to construct a synchronous oscillation source tracing model of a multi-source domain adaptive network by combining the mapping relationship dataset between excitation signal and response signal. A vibration tracing module is used to implement casing vibration tracing under single / multi-point excitation conditions.

Images